CL2022001166A1 - Targeted application of deep learning to automated visual inspection equipment - Google Patents

Targeted application of deep learning to automated visual inspection equipment

Info

Publication number
CL2022001166A1
CL2022001166A1 CL2022001166A CL2022001166A CL2022001166A1 CL 2022001166 A1 CL2022001166 A1 CL 2022001166A1 CL 2022001166 A CL2022001166 A CL 2022001166A CL 2022001166 A CL2022001166 A CL 2022001166A CL 2022001166 A1 CL2022001166 A1 CL 2022001166A1
Authority
CL
Chile
Prior art keywords
container
visual inspection
images
automated visual
deep learning
Prior art date
Application number
CL2022001166A
Other languages
Spanish (es)
Inventor
Neelima Chavali
Thomas C Pearson
Manuel A Soto
Jorge Delgado Torres
Rentas Roberto C Alvarado
Javier O Tapia
Sandra Rodriguez-Toledo
Eric R Flores-Acosta
Osvaldo Perez
Brenda A Torres
Original Assignee
Amgen Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Amgen Inc filed Critical Amgen Inc
Publication of CL2022001166A1 publication Critical patent/CL2022001166A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8803—Visual inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection

Abstract

En un método para potenciar la precisión y la eficiencia en la inspección visual automatizada de recipientes, un recipiente que contiene una muestra se orienta de tal modo que una cámara de exploración de líneas tiene una vista de perfil de un borde de un tapón del recipiente. Una pluralidad de imágenes del borde del tapón es capturada por la primera cámara de exploración de líneas mientras se gira el recipiente, donde cada imagen de la pluralidad de imágenes corresponde a una posición de rotación diferente del recipiente. Se genera una imagen bidimensional del borde del tapón basándose al menos en la pluralidad de imágenes, y píxeles de la imagen bidimensional son procesados, por uno o más procesadores que ejecutan un modelo de inferencia que incluye una red neuronal entrenada, para generar datos de salida indicativos de una probabilidad de que la muestra sea defectuosa.In a method of enhancing accuracy and efficiency in automated visual inspection of containers, a container containing a sample is oriented such that a line scan camera has a profile view of an edge of a container cap. A plurality of images of the cap rim is captured by the first line scan camera while the container is rotated, where each image of the plurality of images corresponds to a different rotational position of the container. A two-dimensional image of the cap rim is generated based on at least the plurality of images, and pixels of the two-dimensional image are processed, by one or more processors executing an inference model including a trained neural network, to generate output data. indicative of a probability that the sample is defective.

CL2022001166A 2019-11-07 2022-05-04 Targeted application of deep learning to automated visual inspection equipment CL2022001166A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201962932413P 2019-11-07 2019-11-07
US201962949667P 2019-12-18 2019-12-18

Publications (1)

Publication Number Publication Date
CL2022001166A1 true CL2022001166A1 (en) 2023-02-10

Family

ID=73654910

Family Applications (1)

Application Number Title Priority Date Filing Date
CL2022001166A CL2022001166A1 (en) 2019-11-07 2022-05-04 Targeted application of deep learning to automated visual inspection equipment

Country Status (12)

Country Link
US (1) US20220398715A1 (en)
EP (1) EP4055559A1 (en)
JP (1) JP2022553572A (en)
KR (1) KR20220090513A (en)
CN (1) CN114631125A (en)
AU (1) AU2020378062A1 (en)
BR (1) BR112022008676A2 (en)
CA (1) CA3153701A1 (en)
CL (1) CL2022001166A1 (en)
IL (1) IL291773A (en)
MX (1) MX2022005355A (en)
WO (1) WO2021092297A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20230153978A1 (en) * 2021-11-17 2023-05-18 Communications Test Design, Inc. Methods and systems for grading devices

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5309486A (en) * 1992-11-12 1994-05-03 Westinghouse Electric Corp. Non-contact flaw detection for cylindrical nuclear fuel pellets

Also Published As

Publication number Publication date
CN114631125A (en) 2022-06-14
EP4055559A1 (en) 2022-09-14
MX2022005355A (en) 2022-06-02
BR112022008676A2 (en) 2022-07-19
WO2021092297A1 (en) 2021-05-14
CA3153701A1 (en) 2021-05-14
JP2022553572A (en) 2022-12-23
US20220398715A1 (en) 2022-12-15
AU2020378062A1 (en) 2022-04-07
IL291773A (en) 2022-06-01
KR20220090513A (en) 2022-06-29

Similar Documents

Publication Publication Date Title
US10467502B2 (en) Surface defect detection
EP3655923B1 (en) Weakly supervised anomaly detection and segmentation in images
US10860879B2 (en) Deep convolutional neural networks for crack detection from image data
US20200125887A1 (en) Tire image recognition method and tire image recognition device
CL2017002353A1 (en) Automated quality control and selection
AR121849A2 (en) A METHOD OF PREPROCESSING A COPIED DIGITAL IMAGE OF A ROOM
WO2020046213A1 (en) A method and apparatus for training a neural network to identify cracks
CN107945200A (en) Image binaryzation dividing method
Thipakorn et al. Egg weight prediction and egg size classification using image processing and machine learning
Salman et al. Leaf classification and identification using Canny Edge Detector and SVM classifier
US10643576B2 (en) System and method for white spot Mura detection with improved preprocessing
Liu et al. Visual attention in deep learning: a review
CL2022001166A1 (en) Targeted application of deep learning to automated visual inspection equipment
Perdana et al. Automatic aerial victim detection on low-cost thermal camera using convolutional neural network
CN109767431A (en) Accessory appearance defect inspection method, device, equipment and readable storage medium storing program for executing
TW201945719A (en) System and method for line defect detection with preprocessing
US11348349B2 (en) Training data increment method, electronic apparatus and computer-readable medium
Liu et al. Deep learning for industrial image: challenges, methods for enriching the sample space and restricting the hypothesis space, and possible issue
Singh et al. Performance analysis of object detection algorithms for robotic welding applications in planar environment
Pérez-Gonzalo et al. Robust wind turbine blade segmentation from RGB images in the wild
RU2560789C1 (en) Method of identification of printing on digital image
Kazmi et al. Vehicle tire (tyre) detection and text recognition using deep learning
Reina Molina et al. Image segmentation using tissue-like P systems with multiple auxiliary cells
Li Fast multi-level connected component labeling for large-scale images
CN109801334A (en) Workpiece localization method, standard point determine method, device and equipment